Research
My research sits at the intersection of physics-grounded engineering models and interpretable computational methods. Current and past areas of interest include:
Interpretable statistical and machine-learning approaches to short- and medium-term energy demand forecasting, with an emphasis on model transparency over black-box accuracy alone.
Physics-informed and data-driven methods for forecasting wind power output, incorporating turbulence, terrain, and turbine-level operating characteristics.
Optimization and control strategies for microgrids integrating distributed generation, storage, and variable renewable sources under real-world operating constraints.
Condition-monitoring and anomaly-detection techniques for rotating equipment, using sensor data to identify early indicators of degradation.
Data-driven and physics-based approaches for detecting anomalies in pipeline systems, drawing on hydraulic modeling and sensor analytics.